End of training
Browse files- README.md +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Apr07_02-08-52_e2b0f09b53b1/events.out.tfevents.1712456719.e2b0f09b53b1.1130.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +400 -0
README.md
CHANGED
|
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the cats_vs_dogs dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
- Accuracy: 0.9919
|
| 37 |
|
| 38 |
## Model description
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the cats_vs_dogs dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.0577
|
| 36 |
- Accuracy: 0.9919
|
| 37 |
|
| 38 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.9918838103374626,
|
| 4 |
+
"eval_loss": 0.05769222229719162,
|
| 5 |
+
"eval_runtime": 27.3788,
|
| 6 |
+
"eval_samples_per_second": 85.504,
|
| 7 |
+
"eval_steps_per_second": 2.703,
|
| 8 |
+
"total_flos": 1.336513820941394e+18,
|
| 9 |
+
"train_loss": 0.2994473668617931,
|
| 10 |
+
"train_runtime": 953.1608,
|
| 11 |
+
"train_samples_per_second": 66.313,
|
| 12 |
+
"train_steps_per_second": 0.516
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.9918838103374626,
|
| 4 |
+
"eval_loss": 0.05769222229719162,
|
| 5 |
+
"eval_runtime": 27.3788,
|
| 6 |
+
"eval_samples_per_second": 85.504,
|
| 7 |
+
"eval_steps_per_second": 2.703
|
| 8 |
+
}
|
runs/Apr07_02-08-52_e2b0f09b53b1/events.out.tfevents.1712456719.e2b0f09b53b1.1130.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd2e139191cd4a929dc4ef2612be6b6426eb6a8b738024d7d4b4e2d2b5309f83
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 1.336513820941394e+18,
|
| 4 |
+
"train_loss": 0.2994473668617931,
|
| 5 |
+
"train_runtime": 953.1608,
|
| 6 |
+
"train_samples_per_second": 66.313,
|
| 7 |
+
"train_steps_per_second": 0.516
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9918838103374626,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-dog-vs-cat/checkpoint-329",
|
| 4 |
+
"epoch": 2.986342943854325,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 492,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"grad_norm": 0.5951987504959106,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.693,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12,
|
| 20 |
+
"grad_norm": 0.743243932723999,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 0.6912,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.18,
|
| 27 |
+
"grad_norm": 0.6900031566619873,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.6871,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.24,
|
| 34 |
+
"grad_norm": 0.7302324175834656,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 0.68,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3,
|
| 41 |
+
"grad_norm": 0.9748005270957947,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 0.6664,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.36,
|
| 48 |
+
"grad_norm": 1.131984829902649,
|
| 49 |
+
"learning_rate": 4.8868778280542986e-05,
|
| 50 |
+
"loss": 0.6408,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.42,
|
| 55 |
+
"grad_norm": 1.0235670804977417,
|
| 56 |
+
"learning_rate": 4.7737556561085976e-05,
|
| 57 |
+
"loss": 0.617,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.49,
|
| 62 |
+
"grad_norm": 1.1163190603256226,
|
| 63 |
+
"learning_rate": 4.660633484162896e-05,
|
| 64 |
+
"loss": 0.5807,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.55,
|
| 69 |
+
"grad_norm": 1.282690405845642,
|
| 70 |
+
"learning_rate": 4.547511312217195e-05,
|
| 71 |
+
"loss": 0.5438,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.61,
|
| 76 |
+
"grad_norm": 1.068588137626648,
|
| 77 |
+
"learning_rate": 4.434389140271493e-05,
|
| 78 |
+
"loss": 0.502,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.67,
|
| 83 |
+
"grad_norm": 0.9256152510643005,
|
| 84 |
+
"learning_rate": 4.321266968325792e-05,
|
| 85 |
+
"loss": 0.4701,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.73,
|
| 90 |
+
"grad_norm": 0.9594171643257141,
|
| 91 |
+
"learning_rate": 4.2081447963800907e-05,
|
| 92 |
+
"loss": 0.447,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.79,
|
| 97 |
+
"grad_norm": 1.0906646251678467,
|
| 98 |
+
"learning_rate": 4.095022624434389e-05,
|
| 99 |
+
"loss": 0.4238,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.85,
|
| 104 |
+
"grad_norm": 0.9434269070625305,
|
| 105 |
+
"learning_rate": 3.981900452488688e-05,
|
| 106 |
+
"loss": 0.4026,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.91,
|
| 111 |
+
"grad_norm": 1.15977144241333,
|
| 112 |
+
"learning_rate": 3.868778280542987e-05,
|
| 113 |
+
"loss": 0.3807,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.97,
|
| 118 |
+
"grad_norm": 0.9563286304473877,
|
| 119 |
+
"learning_rate": 3.7556561085972854e-05,
|
| 120 |
+
"loss": 0.3357,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0,
|
| 125 |
+
"eval_accuracy": 0.9867577958137548,
|
| 126 |
+
"eval_loss": 0.22545380890369415,
|
| 127 |
+
"eval_runtime": 27.2631,
|
| 128 |
+
"eval_samples_per_second": 85.867,
|
| 129 |
+
"eval_steps_per_second": 2.714,
|
| 130 |
+
"step": 164
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.03,
|
| 134 |
+
"grad_norm": 1.0790256261825562,
|
| 135 |
+
"learning_rate": 3.642533936651584e-05,
|
| 136 |
+
"loss": 0.3166,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.09,
|
| 141 |
+
"grad_norm": 0.9720374345779419,
|
| 142 |
+
"learning_rate": 3.529411764705883e-05,
|
| 143 |
+
"loss": 0.2961,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.15,
|
| 148 |
+
"grad_norm": 1.2068029642105103,
|
| 149 |
+
"learning_rate": 3.416289592760181e-05,
|
| 150 |
+
"loss": 0.2753,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.21,
|
| 155 |
+
"grad_norm": 1.0407794713974,
|
| 156 |
+
"learning_rate": 3.3031674208144794e-05,
|
| 157 |
+
"loss": 0.2631,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.27,
|
| 162 |
+
"grad_norm": 0.9938662052154541,
|
| 163 |
+
"learning_rate": 3.1900452488687784e-05,
|
| 164 |
+
"loss": 0.2427,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.34,
|
| 169 |
+
"grad_norm": 0.8150984048843384,
|
| 170 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 171 |
+
"loss": 0.2163,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.4,
|
| 176 |
+
"grad_norm": 0.7988576889038086,
|
| 177 |
+
"learning_rate": 2.9638009049773758e-05,
|
| 178 |
+
"loss": 0.216,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.46,
|
| 183 |
+
"grad_norm": 1.1607186794281006,
|
| 184 |
+
"learning_rate": 2.850678733031674e-05,
|
| 185 |
+
"loss": 0.2086,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.52,
|
| 190 |
+
"grad_norm": 1.0582228899002075,
|
| 191 |
+
"learning_rate": 2.737556561085973e-05,
|
| 192 |
+
"loss": 0.1857,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.58,
|
| 197 |
+
"grad_norm": 0.8427866697311401,
|
| 198 |
+
"learning_rate": 2.6244343891402718e-05,
|
| 199 |
+
"loss": 0.1808,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.64,
|
| 204 |
+
"grad_norm": 0.8713784217834473,
|
| 205 |
+
"learning_rate": 2.51131221719457e-05,
|
| 206 |
+
"loss": 0.1689,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.7,
|
| 211 |
+
"grad_norm": 0.8434356451034546,
|
| 212 |
+
"learning_rate": 2.3981900452488688e-05,
|
| 213 |
+
"loss": 0.1732,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.76,
|
| 218 |
+
"grad_norm": 0.7676334977149963,
|
| 219 |
+
"learning_rate": 2.2850678733031675e-05,
|
| 220 |
+
"loss": 0.1678,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.82,
|
| 225 |
+
"grad_norm": 0.6907545328140259,
|
| 226 |
+
"learning_rate": 2.1719457013574662e-05,
|
| 227 |
+
"loss": 0.1624,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.88,
|
| 232 |
+
"grad_norm": 0.7248879075050354,
|
| 233 |
+
"learning_rate": 2.058823529411765e-05,
|
| 234 |
+
"loss": 0.1613,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.94,
|
| 239 |
+
"grad_norm": 1.4968321323394775,
|
| 240 |
+
"learning_rate": 1.9457013574660635e-05,
|
| 241 |
+
"loss": 0.1683,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.0,
|
| 246 |
+
"eval_accuracy": 0.9918838103374626,
|
| 247 |
+
"eval_loss": 0.05769222229719162,
|
| 248 |
+
"eval_runtime": 27.9863,
|
| 249 |
+
"eval_samples_per_second": 83.648,
|
| 250 |
+
"eval_steps_per_second": 2.644,
|
| 251 |
+
"step": 329
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.0,
|
| 255 |
+
"grad_norm": 1.3721855878829956,
|
| 256 |
+
"learning_rate": 1.832579185520362e-05,
|
| 257 |
+
"loss": 0.1635,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.06,
|
| 262 |
+
"grad_norm": 1.0472960472106934,
|
| 263 |
+
"learning_rate": 1.7194570135746606e-05,
|
| 264 |
+
"loss": 0.1576,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.12,
|
| 269 |
+
"grad_norm": 0.9706544280052185,
|
| 270 |
+
"learning_rate": 1.6063348416289596e-05,
|
| 271 |
+
"loss": 0.157,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.19,
|
| 276 |
+
"grad_norm": 0.6168745756149292,
|
| 277 |
+
"learning_rate": 1.493212669683258e-05,
|
| 278 |
+
"loss": 0.1535,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.25,
|
| 283 |
+
"grad_norm": 2.201444149017334,
|
| 284 |
+
"learning_rate": 1.3800904977375568e-05,
|
| 285 |
+
"loss": 0.1494,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.31,
|
| 290 |
+
"grad_norm": 0.6486875414848328,
|
| 291 |
+
"learning_rate": 1.2669683257918553e-05,
|
| 292 |
+
"loss": 0.1502,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.37,
|
| 297 |
+
"grad_norm": 0.7056523561477661,
|
| 298 |
+
"learning_rate": 1.153846153846154e-05,
|
| 299 |
+
"loss": 0.1446,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.43,
|
| 304 |
+
"grad_norm": 1.3912076950073242,
|
| 305 |
+
"learning_rate": 1.0407239819004526e-05,
|
| 306 |
+
"loss": 0.1428,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.49,
|
| 311 |
+
"grad_norm": 1.0273276567459106,
|
| 312 |
+
"learning_rate": 9.276018099547511e-06,
|
| 313 |
+
"loss": 0.144,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.55,
|
| 318 |
+
"grad_norm": 1.1831059455871582,
|
| 319 |
+
"learning_rate": 8.144796380090498e-06,
|
| 320 |
+
"loss": 0.1572,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.61,
|
| 325 |
+
"grad_norm": 1.5577871799468994,
|
| 326 |
+
"learning_rate": 7.013574660633485e-06,
|
| 327 |
+
"loss": 0.1419,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.67,
|
| 332 |
+
"grad_norm": 1.2978945970535278,
|
| 333 |
+
"learning_rate": 5.882352941176471e-06,
|
| 334 |
+
"loss": 0.1562,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.73,
|
| 339 |
+
"grad_norm": 0.5621709823608398,
|
| 340 |
+
"learning_rate": 4.751131221719457e-06,
|
| 341 |
+
"loss": 0.1352,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.79,
|
| 346 |
+
"grad_norm": 1.0484684705734253,
|
| 347 |
+
"learning_rate": 3.619909502262444e-06,
|
| 348 |
+
"loss": 0.143,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.85,
|
| 353 |
+
"grad_norm": 0.9431272149085999,
|
| 354 |
+
"learning_rate": 2.48868778280543e-06,
|
| 355 |
+
"loss": 0.1517,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.91,
|
| 360 |
+
"grad_norm": 0.8055468201637268,
|
| 361 |
+
"learning_rate": 1.3574660633484164e-06,
|
| 362 |
+
"loss": 0.1455,
|
| 363 |
+
"step": 480
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.97,
|
| 367 |
+
"grad_norm": 1.1355047225952148,
|
| 368 |
+
"learning_rate": 2.2624434389140275e-07,
|
| 369 |
+
"loss": 0.1448,
|
| 370 |
+
"step": 490
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.99,
|
| 374 |
+
"eval_accuracy": 0.9918838103374626,
|
| 375 |
+
"eval_loss": 0.04604041948914528,
|
| 376 |
+
"eval_runtime": 27.4499,
|
| 377 |
+
"eval_samples_per_second": 85.283,
|
| 378 |
+
"eval_steps_per_second": 2.696,
|
| 379 |
+
"step": 492
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.99,
|
| 383 |
+
"step": 492,
|
| 384 |
+
"total_flos": 1.336513820941394e+18,
|
| 385 |
+
"train_loss": 0.2994473668617931,
|
| 386 |
+
"train_runtime": 953.1608,
|
| 387 |
+
"train_samples_per_second": 66.313,
|
| 388 |
+
"train_steps_per_second": 0.516
|
| 389 |
+
}
|
| 390 |
+
],
|
| 391 |
+
"logging_steps": 10,
|
| 392 |
+
"max_steps": 492,
|
| 393 |
+
"num_input_tokens_seen": 0,
|
| 394 |
+
"num_train_epochs": 3,
|
| 395 |
+
"save_steps": 500,
|
| 396 |
+
"total_flos": 1.336513820941394e+18,
|
| 397 |
+
"train_batch_size": 32,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|